Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
skip to main content
10.1145/3474717.3483920acmconferencesArticle/Chapter ViewAbstractPublication PagesgisConference Proceedingsconference-collections
research-article

DetectorNet: Transformer-enhanced Spatial Temporal Graph Neural Network for Traffic Prediction

Published: 04 November 2021 Publication History

Abstract

Detectors with high coverage have direct and far-reaching benefits for road users in route planning and avoiding traffic congestion, but utilizing these data presents unique challenges including: the dynamic temporal correlation, and the dynamic spatial correlation caused by changes in road conditions. Although the existing work considers the significance of modeling with spatial-temporal correlation, what it has learned is still a static road network structure, which cannot reflect the dynamic changes of roads, and eventually loses much valuable potential information. To address these challenges, we propose DetectorNet enhanced by Transformer. Differs from previous studies, our model contains a Multi-view Temporal Attention module and a Dynamic Attention module, which focus on the long-distance and short-distance temporal correlation, and dynamic spatial correlation by dynamically updating the learned knowledge respectively, so as to make accurate prediction. In addition, the experimental results on two public datasets and the comparison results of four ablation experiments proves that the performance of DetectorNet is better than the eleven advanced baselines.

References

[1]
Weiqi Chen, Ling Chen, Yu Xie, Wei Cao, Yusong Gao, and Xiaojie Feng. 2020. Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting. In The Thirty-Fourth AAAI Conference on Artificial Intelligence. 3529--3536.
[2]
Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, Xiaojun Chang, and Chengqi Zhang. 2020. Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks. In KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 753--763.
[3]
Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, and Chengqi Zhang. 2019. Graph WaveNet for Deep Spatial-Temporal Graph Modeling. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI, Sarit Kraus (Ed.). 1907--1913.
[4]
Junbo Zhang, Yu Zheng, Junkai Sun, and Dekang Qi. 2020. Flow Prediction in Spatio-Temporal Networks Based on Multitask Deep Learning. IEEE Trans. Knowl. Data Eng. 32, 3 (2020), 468--478.
[5]
Chuanpan Zheng, Xiaoliang Fan, Cheng Wang, and Jianzhong Qi. 2020. GMAN: A Graph Multi-Attention Network for Traffic Prediction. In The Thirty-Fourth AAAI Conference on Artificial Intelligence. 1234--1241.

Cited By

View all
  • (2025)A traffic prediction method for missing data scenarios: graph convolutional recurrent ordinary differential equation networkComplex & Intelligent Systems10.1007/s40747-024-01768-711:2Online publication date: 15-Jan-2025
  • (2025)TDMixer: Lightweight Long-Term Series Forecasting using Time-Continuous Embedding and Magnitude DecompositionDatabase Systems for Advanced Applications10.1007/978-981-97-5779-4_14(211-226)Online publication date: 11-Jan-2025
  • (2024)HumanTOMATOProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3693407(32939-32977)Online publication date: 21-Jul-2024
  • Show More Cited By

Index Terms

  1. DetectorNet: Transformer-enhanced Spatial Temporal Graph Neural Network for Traffic Prediction

      Recommendations

      Comments

      Information & Contributors

      Information

      Published In

      cover image ACM Conferences
      SIGSPATIAL '21: Proceedings of the 29th International Conference on Advances in Geographic Information Systems
      November 2021
      700 pages
      ISBN:9781450386647
      DOI:10.1145/3474717
      Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

      Sponsors

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      Published: 04 November 2021

      Permissions

      Request permissions for this article.

      Check for updates

      Author Tags

      1. Graph Neural Network
      2. Self-attention
      3. Spatial-Temporal Graph
      4. Traffic Prediction

      Qualifiers

      • Research-article
      • Research
      • Refereed limited

      Funding Sources

      • Natural Science Foundation of Shaanxi Province
      • National Natural Science Foundation of China
      • National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT)
      • MSIT(Ministry of Science and ICT), Korea, under the Grand Information Technology Research Center support program

      Conference

      SIGSPATIAL '21
      Sponsor:

      Acceptance Rates

      Overall Acceptance Rate 257 of 1,238 submissions, 21%

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • Downloads (Last 12 months)56
      • Downloads (Last 6 weeks)6
      Reflects downloads up to 10 Feb 2025

      Other Metrics

      Citations

      Cited By

      View all
      • (2025)A traffic prediction method for missing data scenarios: graph convolutional recurrent ordinary differential equation networkComplex & Intelligent Systems10.1007/s40747-024-01768-711:2Online publication date: 15-Jan-2025
      • (2025)TDMixer: Lightweight Long-Term Series Forecasting using Time-Continuous Embedding and Magnitude DecompositionDatabase Systems for Advanced Applications10.1007/978-981-97-5779-4_14(211-226)Online publication date: 11-Jan-2025
      • (2024)HumanTOMATOProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3693407(32939-32977)Online publication date: 21-Jul-2024
      • (2024)A Dual-Stream Cross AGFormer-GPT Network for Traffic Flow Prediction Based on Large-Scale Road Sensor DataSensors10.3390/s2412390524:12(3905)Online publication date: 17-Jun-2024
      • (2024)ERASE: Error-Resilient Representation Learning on Graphs for Label Noise ToleranceProceedings of the 33rd ACM International Conference on Information and Knowledge Management10.1145/3627673.3679552(270-280)Online publication date: 21-Oct-2024
      • (2024)Dynamic Graph Representation Learning With Neural Networks: A SurveyIEEE Access10.1109/ACCESS.2024.337811112(43460-43484)Online publication date: 2024
      • (2024)Spatial–temporal combination and multi-head flow-attention network for traffic flow predictionScientific Reports10.1038/s41598-024-60337-714:1Online publication date: 26-Apr-2024
      • (2024)IEDSFAN: information enhancement and dynamic-static fusion attention network for traffic flow forecastingComplex & Intelligent Systems10.1007/s40747-024-01663-111:1Online publication date: 13-Nov-2024
      • (2024)STA-former: encoding traffic flows with spatio-temporal associations in transformer networks for predictionCluster Computing10.1007/s10586-024-04462-y27:7(9693-9714)Online publication date: 1-Oct-2024
      • (2023)SOCDet: A Lightweight and Accurate Oriented Object Detection Network for Satellite On-Orbit ComputingIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2023.326964261(1-15)Online publication date: 2023
      • Show More Cited By

      View Options

      Login options

      View options

      PDF

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Figures

      Tables

      Media

      Share

      Share

      Share this Publication link

      Share on social media